© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 10785
    Prev
    Next
    INDEX
    Explanations

    references to staff and human resources in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ultimatum
    -0.43
     HYPER
    -0.42
    getPoint
    -0.41
    URLException
    -0.41
     NEXT
    -0.40
     DEFINITION
    -0.39
     next
    -0.39
    URLConnection
    -0.38
     Burnham
    -0.38
    beten
    -0.38
    POSITIVE LOGITS
     staff
    0.96
     Staff
    0.96
    Staff
    0.93
     staffs
    0.85
     STAFF
    0.84
    STAFF
    0.79
    staff
    0.76
     employees
    0.75
     medewerkers
    0.75
    Employees
    0.74
    Activations Density 0.177%

    No Known Activations